hgext/fastexport.py

branchmap-v3: introduce a "stop_rev" argument to `headsrevs`

The `headsrevs` method of the revlog already have a `revs` argument to compute
the headrevs of a limited set of heads. However, it disable the use of the
native compiled code to compute the heads, which slows down the branchmap v3
code a lot.

The branchmap v3 usage is actually quite constrained as we will always only
ignores a part at the top of the graph. So we could be significantly faster.

We start by making small change to the python side to improve the situation and
introduce the new API. More collaboration with the native code are coming later.

This massively speedup operation and close most of the remaining gaps between
branchmap-v3 and branchmap-v2. especially on repository with many revs like
mozilla-try. A small overhead remains mostly because the `headrevs` logic
currently has some inefficiently. We will look into them from there.

### benchmark.name                                 = hg.command.unbundle
  # bin-env-vars.hg.py-re2-module                  = default
  # benchmark.variants.issue6528                   = disabled
  # benchmark.variants.resource-usage              = default
  # benchmark.variants.reuse-external-delta-parent = yes
  # benchmark.variants.revs                        = any-1-extra-rev
  # benchmark.variants.source                      = unbundle
  # benchmark.variants.validate                    = default
  # benchmark.variants.verbosity                   = quiet

 ## data-env-vars.name                             = netbeans-2018-08-01-zstd-sparse-revlog
  # bin-env-vars.hg.flavor                         = default
branch-v2:        0.233711  ~~~~~
branch-v3 before: 0.368769  (+57.79%, +0.14)
branch-v3 after:  0.239857   (+2.63%, +0.01)
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.235230  ~~~~~
branch-v3 before: 0.372460  (+58.34%, +0.14)
branch-v3 after:  0.240972   (+2.44%, +0.01)
 ## data-env-vars.name                             = netbeans-2018-08-01-ds2-pnm
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.255586  ~~~~~
branch-v3 before: 0.318907  (+24.78%, +0.06)
branch-v3 after:  0.268560   (+5.08%, +0.01)

 ## data-env-vars.name                             = mozilla-central-2024-03-22-zstd-sparse-revlog
  # bin-env-vars.hg.flavor                         = default
branch-v2:        0.339010  ~~~~~
branch-v3 before: 0.349752   (+3.17%, +0.01)
branch-v3 after:  0.349389   (+3.06%, +0.01)
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.346525  ~~~~~
branch-v3 before: 0.354300   (+2.24%, +0.01)
branch-v3 after:  0.355661   (+2.64%, +0.01)
 ## data-env-vars.name                             = mozilla-central-2024-03-22-ds2-pnm
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.380202  ~~~~~
branch-v3 before: 0.396293   (+4.23%, +0.02)
branch-v3 after:  0.408851   (+7.54%, +0.03)

 ## data-env-vars.name                             = mozilla-unified-2024-03-22-zstd-sparse-revlog
  # bin-env-vars.hg.flavor                         = default
branch-v2:        0.412165  ~~~~~
branch-v3 before: 0.424769   (+3.06%, +0.01)
branch-v3 after:  0.427782   (+3.79%, +0.02)
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.412397  ~~~~~
branch-v3 before: 0.421796   (+2.28%, +0.01)
branch-v3 after:  0.422354   (+2.41%, +0.01)
 ## data-env-vars.name                             = mozilla-unified-2024-03-22-ds2-pnm
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        0.429501  ~~~~~
branch-v3 before: 0.443849   (+3.34%, +0.01)
branch-v3 after:  0.443197   (+3.19%, +0.01)

 ## data-env-vars.name                             = mozilla-try-2024-03-26-zstd-sparse-revlog
  # bin-env-vars.hg.flavor                         = default
branch-v2:        3.403171  ~~~~~
branch-v3 before: 6.234055  (+83.18%, +2.83)
branch-v3 after:  3.819477  (+12.23%, +0.42)
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        3.454876  ~~~~~
branch-v3 before: 6.307813  (+82.58%, +2.85)
branch-v3 after:  3.590284   (+3.92%, +0.14)
 ## data-env-vars.name                             = mozilla-try-2024-03-26-ds2-pnm
  # bin-env-vars.hg.flavor                         = rust
branch-v2:        3.465435  ~~~~~
branch-v3 before: 5.176076  (+49.36%, +1.71)
branch-v3 after:  3.633278   (+4.84%, +0.17)

# Copyright 2020 Joerg Sonnenberger <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""export repositories as git fast-import stream"""

# The format specification for fast-import streams can be found at
# https://git-scm.com/docs/git-fast-import#_input_format

from __future__ import annotations

import re

from mercurial.i18n import _
from mercurial.node import hex, nullrev
from mercurial.utils import stringutil
from mercurial import (
    error,
    logcmdutil,
    registrar,
    scmutil,
)
from .convert import convcmd

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b"ships-with-hg-core"

cmdtable = {}
command = registrar.command(cmdtable)

GIT_PERSON_PROHIBITED = re.compile(b'[<>\n"]')
GIT_EMAIL_PROHIBITED = re.compile(b"[<> \n]")


def convert_to_git_user(authormap, user, rev):
    mapped_user = authormap.get(user, user)
    user_person = stringutil.person(mapped_user)
    user_email = stringutil.email(mapped_user)
    if GIT_EMAIL_PROHIBITED.match(user_email) or GIT_PERSON_PROHIBITED.match(
        user_person
    ):
        raise error.Abort(
            _(b"Unable to parse user into person and email for revision %s")
            % rev
        )
    if user_person:
        return b'"%s" <%s>' % (user_person, user_email)
    else:
        return b"<%s>" % user_email


def convert_to_git_date(date):
    timestamp, utcoff = date
    tzsign = b"+" if utcoff <= 0 else b"-"
    if utcoff % 60 != 0:
        raise error.Abort(
            _(b"UTC offset in %b is not an integer number of seconds") % (date,)
        )
    utcoff = abs(utcoff) // 60
    tzh = utcoff // 60
    tzmin = utcoff % 60
    return b"%d " % int(timestamp) + tzsign + b"%02d%02d" % (tzh, tzmin)


def convert_to_git_ref(branch):
    # XXX filter/map depending on git restrictions
    return b"refs/heads/" + branch


def write_data(buf, data, add_newline=False):
    buf.append(b"data %d\n" % len(data))
    buf.append(data)
    if add_newline or data[-1:] != b"\n":
        buf.append(b"\n")


def export_commit(ui, repo, rev, marks, authormap):
    ctx = repo[rev]
    revid = ctx.hex()
    if revid in marks:
        ui.debug(b"warning: revision %s already exported, skipped\n" % revid)
        return
    parents = [p for p in ctx.parents() if p.rev() != nullrev]
    for p in parents:
        if p.hex() not in marks:
            ui.warn(
                _(b"warning: parent %s of %s has not been exported, skipped\n")
                % (p, revid)
            )
            return

    # For all files modified by the commit, check if they have already
    # been exported and otherwise dump the blob with the new mark.
    for fname in ctx.files():
        if fname not in ctx:
            continue
        filectx = ctx.filectx(fname)
        filerev = hex(filectx.filenode())
        if filerev not in marks:
            mark = len(marks) + 1
            marks[filerev] = mark
            data = filectx.data()
            buf = [b"blob\n", b"mark :%d\n" % mark]
            write_data(buf, data, True)
            ui.write(*buf, keepprogressbar=True)
            del buf

    # Assign a mark for the current revision for references by
    # latter merge commits.
    mark = len(marks) + 1
    marks[revid] = mark

    ref = convert_to_git_ref(ctx.branch())
    buf = [
        b"commit %s\n" % ref,
        b"mark :%d\n" % mark,
        b"committer %s %s\n"
        % (
            convert_to_git_user(authormap, ctx.user(), revid),
            convert_to_git_date(ctx.date()),
        ),
    ]
    write_data(buf, ctx.description())
    if parents:
        buf.append(b"from :%d\n" % marks[parents[0].hex()])
    if len(parents) == 2:
        buf.append(b"merge :%d\n" % marks[parents[1].hex()])
        p0ctx = repo[parents[0]]
        files = ctx.manifest().diff(p0ctx.manifest())
    else:
        files = ctx.files()
    filebuf = []
    for fname in files:
        if fname not in ctx:
            filebuf.append((fname, b"D %s\n" % fname))
        else:
            filectx = ctx.filectx(fname)
            filerev = filectx.filenode()
            fileperm = b"755" if filectx.isexec() else b"644"
            changed = b"M %s :%d %s\n" % (fileperm, marks[hex(filerev)], fname)
            filebuf.append((fname, changed))
    filebuf.sort()
    buf.extend(changed for (fname, changed) in filebuf)
    del filebuf
    buf.append(b"\n")
    ui.write(*buf, keepprogressbar=True)
    del buf


isrev = re.compile(b"^[0-9a-f]{40}$")


@command(
    b"fastexport",
    [
        (b"r", b"rev", [], _(b"revisions to export"), _(b"REV")),
        (b"i", b"import-marks", b"", _(b"old marks file to read"), _(b"FILE")),
        (b"e", b"export-marks", b"", _(b"new marks file to write"), _(b"FILE")),
        (
            b"A",
            b"authormap",
            b"",
            _(b"remap usernames using this file"),
            _(b"FILE"),
        ),
    ],
    _(b"[OPTION]... [REV]..."),
    helpcategory=command.CATEGORY_IMPORT_EXPORT,
)
def fastexport(ui, repo, *revs, **opts):
    """export repository as git fast-import stream

    This command lets you dump a repository as a human-readable text stream.
    It can be piped into corresponding import routines like "git fast-import".
    Incremental dumps can be created by using marks files.
    """
    revs += tuple(opts.get("rev", []))
    if not revs:
        revs = scmutil.revrange(repo, [b":"])
    else:
        revs = logcmdutil.revrange(repo, revs)
    if not revs:
        raise error.Abort(_(b"no revisions matched"))
    authorfile = opts.get("authormap")
    if authorfile:
        authormap = convcmd.readauthormap(ui, authorfile)
    else:
        authormap = {}

    import_marks = opts.get("import_marks")
    marks = {}
    if import_marks:
        with open(import_marks, "rb") as import_marks_file:
            for line in import_marks_file:
                line = line.strip()
                if not isrev.match(line) or line in marks:
                    raise error.Abort(_(b"Corrupted marks file"))
                marks[line] = len(marks) + 1

    revs.sort()
    with ui.makeprogress(
        _(b"exporting"), unit=_(b"revisions"), total=len(revs)
    ) as progress:
        for rev in revs:
            export_commit(ui, repo, rev, marks, authormap)
            progress.increment()

    export_marks = opts.get("export_marks")
    if export_marks:
        with open(export_marks, "wb") as export_marks_file:
            output_marks = [None] * len(marks)
            for k, v in marks.items():
                output_marks[v - 1] = k
            for k in output_marks:
                export_marks_file.write(k + b"\n")